Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3618 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4316. Min Range: -4.4316
Max Act: 4.4316. Min Act: -0.1700
Data Index: 2826311 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4316. Min Range: -4.4316
Max Act: 4.2441. Min Act: -0.1700
Data Index: 7903832 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4316. Min Range: -4.4316
Max Act: 4.2441. Min Act: -0.1700
Data Index: 581573 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4316. Min Range: -4.4316
Max Act: 4.1815. Min Act: -0.1700
Data Index: 6489555 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4316. Min Range: -4.4316
Max Act: 4.1503. Min Act: -0.1700
Data Index: 4539863 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4316. Min Range: -4.4316
Max Act: 4.1503. Min Act: -0.1700
Data Index: 3508232 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4316. Min Range: -4.4316
Max Act: 4.1815. Min Act: -0.1700
Data Index: 7437586 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4316. Min Range: -4.4316
Max Act: 4.0565. Min Act: -0.1700
Data Index: 73769 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4316. Min Range: -4.4316
Max Act: 4.0253. Min Act: -0.1700
Data Index: 7422119 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4316. Min Range: -4.4316
Max Act: 3.9940. Min Act: -0.1700
Data Index: 1916957 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4316. Min Range: -4.4316
Max Act: 4.0253. Min Act: -0.1700
Data Index: 8417953 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4316. Min Range: -4.4316
Max Act: 4.0253. Min Act: -0.1700
Data Index: 3836871 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4316. Min Range: -4.4316
Max Act: 3.9940. Min Act: -0.1700
Data Index: 2009748 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4316. Min Range: -4.4316
Max Act: 3.9627. Min Act: -0.1700
Data Index: 3879676 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4316. Min Range: -4.4316
Max Act: 3.9940. Min Act: -0.1700
Data Index: 5462941 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4316. Min Range: -4.4316
Max Act: 3.9940. Min Act: -0.1700
Data Index: 5389264 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4316. Min Range: -4.4316
Max Act: 3.9315. Min Act: -0.1700
Data Index: 2584327 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4316. Min Range: -4.4316
Max Act: 3.9627. Min Act: -0.1700
Data Index: 7463957 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4316. Min Range: -4.4316
Max Act: 3.9940. Min Act: -0.1700
Data Index: 8093989 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4316. Min Range: -4.4316
Max Act: 3.9627. Min Act: -0.1700
Data Index: 433662 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19